educational AI-powered resources on the basis of student progress. Dynamic difficulty adjustment allows content to be adapted to the learner’s level of proficiency. Through the identification of learning

The gap

Consensus across the literature

Supporting evidence — 4 representative gaps

• Artificial Intelligence–Powered Adaptive Learning Systems in Technical and Vocational Education: Effects on Skill Mastery, Self-Regulated Learning, and Learner Autonomy (2026) · doi

  adaptive platforms: Prioritize learning systems that offer real-time diagnostics, personalized content sequencing, and feedback mechanisms to support individualized learning pathways for students. This aligns with broader evidence showing that adaptive systems can enhance learner engagement and outcomes when pedagogically sound and well-implemented. learning: Teachers should be empowered not just as content deliverers but as coaches and data interpreters who can guide students in interpreting their progress analytics and making productive learning decisions. This dual role enhances the benefit of adaptive systems. instructors as facilitators of b. Train c. Blend technology with hands-on practice: Adaptive systems should complement but not replace practical, hands-on TVET experiences. Tools like AI-powered platforms can prepare learners for workshop tasks and real-world practice, but physical performance evaluation remains essential. learning analytics b. Use blended data sources: Future studies should integrate trace data (e.g., interaction logs, time-on-task, error rates) with to deepen traditional performance measures understanding of feedback influences learning behaviour. adaptive how c. Explore hybrid AI models: Investigate how emerging techniques, such as generative AI and reinforcement improve adaptive instruction, especially for complex vocational tasks that require creative problem solving. learning, can further REFERENCES [1] Hariyanto, F. X. D., Kristianingsih, F. X. D., & Maharani, R. (2025). Artificial intelligence in adaptive education: a systematic review of techniques for personalized learning. Discover Education. [2] Holmes, W., Bialik, M., & Fadel, C. (2019). Artificial intelligence in education: Promises and implications for teaching and learning. Center for Curriculum Redesign. [3] Kulik, J. A., & Fletcher, J. D. (2016). Effectiveness of intelligent tutoring systems. Review of Educational Research, 86(1), 42–78. https://doi.org/10.3102/0034654315581420 IRE 1716175 ICONIC RESEARCH AND ENGINEERING JOURNALS 1350 © APR 2026 | IRE Journals | Volume 9 Issue 10 | ISSN: 2456-8880 DOI: https://doi.org/10.64388/IREV9I10-1716175 [4] Le Ying Tan, S., Hu, S., Yeo, D. J., & Cheong, K. H. (2025). Artificial intelligence-enabled adaptive A review.Computers & Artificial Intelligence. platforms: learning [5] Little, D. (2015). Learning as dialogue: The dependence of learner autonomy on teacher autonomy. System, 23(2), 175–181. [6] Pane, J. F., Steiner, E. D., Baird, M. D., & Hamilton, L. S. (2017). Informing progress:

  Keywords: learning adaptive systems artificial intelligence platforms education review real time personalized content feedback students learner
• The impact of AI precision feedback on college students’ thinking shaping ability: mediating effect of intrinsic value identification and moderating role of critical consciousness transformation (2026) · doi

  in conventional With the rapid advancement of artificial intelligence technology, its applications in education have become increasingly widespread and profound, with AI precision feedback emerging as a key research focus (Li et al., 2025). Numerous studies demonstrate that AI precision feed- back systems offer significant advantages over traditional methods, effectively overcoming feedback approaches (Navio-Ingles et al., 2025). Traditional feedback mecha- nisms are often constrained by teachers’ time and energy, making it challenging to provide comprehensive, detailed, and timely feedback for every student (Pears et al., 2025). In contrast, AI leverages its robust data processing capabilities to collect and analyze students’ learning data in real-time, covering multiple aspects such as learning behaviors, test-taking performance, and knowledge mastery levels. This enables the delivery of precise, personalized feedback tailored to individual needs (Preda-ulita, 2025). For instance, some intelligent learning systems can accurately identify students’ knowledge gaps based on error patterns in their test answers, then recommend tar- geted learning materials and practice questions to help students effec- tively address knowledge deficiencies and enhance learning outcomes. Such precision feedback not only helps students promptly understand their academic progress but also motivates them to engage more actively in their learning process (Steiss et al., 2024; Yan, 2025). From the theoretical evolution of feedback mechanisms, AI-powered precision feedback represents a paradigm shift in educa- tional feedback from “delayed-unified” to “real-time-personalized” approaches. The feedback model proposed by Hattie and Timperley emphasizes that “feedback answers three fundamental questions: Where am I headed? How do I get there? What’s next?” AI precision feedback extends this theory through data mining technologies. Specifically, its accuracy manifests in three dimensions: content preci- sion (identifying specific cognitive gaps using knowledge graphs), timing precision (predicting optimal intervention points based on learning curves), and method precision (personalized presentation formats tailored to learner profiles). Recent research has further cat- egorized AI feedback into three tiers: first-level outcome feedback (correct/incorrect judgments), second-level process feedback (error type diagnosis), and third-level metacognitive feedback (strategic rec- ommendations and cognitive monitoring). This study focuses on the profound impact of third-level feedback on cognitive shaping capabili- ties, a feedback mechanism that remains inadequately explored in existing literature. 2.2 College students’ thinking shaping ability The ability of college students’ thinking shaping is the key compo- nent of their comprehensive quality, which plays a vital role in their future development (Dane

  Keywords: feedback precision learning students knowledge level time personalized three cognitive shaping profound systems traditional approaches
• METHODOLOGICAL RECOMMENDATIONS ON THE EFFECTIVE USE OF ARTIFICIAL INTELLIGENCE IN ENGLISH LANGUAGE TEACHING IN UZBEK CLASSES (2026) · doi

  Artificial intelligence has undergone remarkable that meet the needs of today’s learners. Students advancement in recent years, exerting a profound are more engaged with technology-based learning and far-reaching influence across numerous environments, and artificial intelligence provides dimensions of contemporary life, with the opportunities to create interactive, learner- educational sphere being among the most centered, and personalized lessons. AI tools significantly affected. Modern teaching requires can assist teachers in organizing instruction, teachers not only to possess subject knowledge, monitoring learner progress, and providing timely but also to effectively use digital technologies in feedback. the learning process. In this context, artificial intelligence has become an important supportive tool for improving the quality and effectiveness of English language teaching.

  Keywords: artificial intelligence learning learner teaching teachers undergone remarkable meet needs today learners students advancement recent
• Proposed vision for developing an adaptive e-learning environment based on artificial intelligence: a theoretically-grounded framework and its suitability from the perspective of experts (2026) · doi

  educational AI-powered resources on the basis of student progress. Dynamic difficulty adjustment allows content to be adapted to the learner’s level of proficiency. Through the identification of learning styles (visual, auditory, and kinesthetic), content delivery is customized. suggest reduced by automating administrative identify at-risk students and recommend language processing enables AI Real-time assessment enables automated feedback and the grading of assignments and quizzes. Predictive analytics are used interventions. to

  Keywords: content enables educational powered resources basis student progress dynamic culty adjustment allows adapted learner level